Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10765
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quality or performance levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    わる
    -0.60
    tec
    -0.58
    はず
    -0.55
     Sándor
    -0.55
    みる
    -0.55
    する
    -0.54
     a
    -0.54
    пада
    -0.53
     the
    -0.53
     erfüllt
    -0.53
    POSITIVE LOGITS
    AsUp
    1.01
     kasarigan
    0.88
     فريبيس
    0.84
    ")->
    0.84
     autorytatywna
    0.82
     تضيفلها
    0.81
    tanleria
    0.80
     insuffisamment
    0.80
    ={({
    0.78
     μην
    0.78
    Activations Density 0.523%

    No Known Activations